Meta AI

Llama 2 13B Chat

Type
language model
Context
4K tokens
Max output
4K
API string
replicate/meta/llama-2-13b-chat

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Replicate $0.1 $0.5 31 Jul 2026
Amazon Bedrock $0.75 $1 2 Aug 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score in English 1,120.03 1,112–1,128 — —
Arena Score in Spanish 1,085.77 1,046–1,125 — —
Arena Score, overall 1,084.62 1,078–1,091 — —
Arena Score, mathematics 1,064.92 1,052–1,078 — —
Arena Score, long queries 1,064.44 1,047–1,082 — —
Arena Score, programming 1,062.81 1,050–1,076 — —
Arena Score in Russian 1,053.56 1,033–1,074 — —
Arena Score, hard prompts 1,051.22 1,041–1,061 — —
Arena Score, multi-turn dialogue 1,050.17 1,036–1,064 — —
Arena Score, creative writing 1,047.27 1,035–1,060 — —
Arena Score, instruction following 1,045.79 1,037–1,055 — —
Arena Score in French 1,042.86 1,003–1,083 — —
Arena Score, expert questions 1,029.54 1,004–1,055 — —